Methods and systems for tagged image generation

Abstract

A method, system, and computer program product generate at least one tagged image, and include the feature of determining at least one user content image from at least one subject image. There are also the features of identifying at least one product in the obtained user content image using at least one artificial intelligence model, and generating at least one tagged image with the identified product or products in the obtained user content image or images.

What is claimed: 
     
         1 . A method for generating at least one tagged image, the method comprising
 determining at least one user content image from at least one subject image;   identifying at least one product in the obtained at least one user content image using at least one artificial intelligence model; and   generating the at least one tagged image comprising the identified at least one product in the obtained at least one user content image.   
     
     
         2 . The method of  claim 1 , wherein the identifying of the at least one product comprises:
 determining a match between the identified at least one product and a product catalogue based on at least one of an identity information of the identified at least one product or a location of the identified at least one product in the determined at least one user content image; and   generating a scored list of the determined match between the identified at least one product and the product catalogue.   
     
     
         3 . The method of  claim 2 , wherein the location of the identified at least one product in the determined at least one user content image is within bounding box co-ordinates defined in the determined at least one user content image. 
     
     
         4 . The method of  claim 1 , further comprising training the at least one artificial intelligence model using training data, wherein the training data comprises images of a plurality of products in at least one of a plurality of sample user content images or the product catalogue as an input to the artificial intelligence model and identity information of the plurality of products in the product catalogue as an output of the artificial intelligence model. 
     
     
         5 . The method of  claim 3 , wherein the training data is labelled based on at least one of one or more colors of the plurality of products, one or more categories of the plurality of products, gender appropriateness of the plurality of products, age appropriateness of the plurality of products, or locations of the plurality of products in the sample user content images. 
     
     
         6 . The method of  claim 3 , further comprising obtaining the training data from a plurality of data crowdsourcing service providers. 
     
     
         7 . The method of  claim 1 , wherein the product catalog is one of a fashion related product catalog, a travel and leisure related product catalog, a sports and equipment related product catalog a health and beauty catalog, a consumer packaged goods catalog, or a home décor and furniture catalog. 
     
     
         8 . The method of  claim 1 , wherein the at least one artificial intelligence model is one of a neural network, a nearest neighbor model, a k-nearest neighbor clustering model, a singular value decomposition model, a principal component analysis model, or an entity embeddings model. 
     
     
         9 . A system for generating at least one tagged image, the method comprising at least one memory configured to store computer program code instructions; and
 at least one processor configured to execute the computer program code instructions to:   determine at least one user content image from the at least one subject image;   identify at least one product in the obtained at least one user content image using at least one artificial intelligence model; and   generate the at least one tagged image comprising the identified at least product in the obtained at least one user content image.   
     
     
         10 . The system of  claim 9 , for identifying of the at least one product, the at least one processor is configured to:
 determine a match between the identified at least one product and a product catalogue based on at least one of an identity information of the identified at least one product or a location of the identified at least one product in the determined at least one user content image; and   generate a scored list of the determined match between the identified at least one product and the product catalogue.   
     
     
         11 . The system of  claim 10 , wherein the location of the identified at least one product in the determined at least one user content image is within bounding box co-ordinates defined in the determined at least one user content image. 
     
     
         12 . The system of  claim 9 , wherein the at least one processor is further configured to train the at least one artificial intelligence model using training data, wherein the training data comprises images of a plurality of products in at least one of a plurality of sample user content images or the product catalogue as an input to the artificial intelligence model and identity information of the plurality of products in the product catalogue as an output of the artificial intelligence model. 
     
     
         13 . The system of  claim 12 , wherein the training data is labelled based on at least one of one or more colors of the plurality of products, one or more categories of the plurality of products, gender appropriateness of the plurality of products, age appropriateness of the plurality of products, or locations of the plurality of products in the sample user content images. 
     
     
         14 . The system of  claim 12 , wherein the at least one processor is further configured to obtain the training data from a plurality of data crowdsourcing service providers. 
     
     
         15 . The system of  claim 9 , wherein the product catalogue is one of a fashion related product catalogue, a travel and leisure related product catalogue, a sports and equipment related product catalogue, a health and beauty catalogue, a consumer packaged goods catalogue, or a home décor and furniture catalogue. 
     
     
         16 . The system of  claim 9 , wherein the at least one artificial intelligence model is one of a neural network model, a nearest neighbor model, a k-nearest neighbor clustering model, a singular value decomposition model, a principal component analysis model, or an entity embeddings model. 
     
     
         17 . A computer program product comprising at least one non-transitory computer-readable storage medium having stored thereon computer-executable program code instructions which when executed by a computer, cause the computer to carry out operations for generating at least one tagged image, the operations comprising:
 determining at least one user content image from the at least one subject image;   identifying at least one product in the obtained at least one user content image using at least one artificial intelligence model; and   generating the at least one tagged image comprising the identified at least product in the obtained at least one user content image.   
     
     
         18 . The computer program product of  claim 17 , wherein the operations for identifying of the at least one product further comprises:
 determining a match between the identified at least one product and a product catalogue based on at least one of an identity information of the identified at least one product or a location of the identified at least one product in the determined at least one user content image; and   generating a scored list of the determined match between the identified at least one product and the product catalogue.   
     
     
         19 . The computer program product of  claim 17 , wherein the operations further comprise training the at least one artificial intelligence model using training data, wherein the training data comprises images of a plurality of products in at least one of a plurality of sample user content images or the product catalogue as an input to the artificial intelligence model or identity information of the plurality of products in the product catalogue as an output of the artificial intelligence model. 
     
     
         20 . The computer program product of  claim 19 , wherein the operations further comprise obtaining the training data from a plurality of data crowdsourcing service providers.